Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Medical Visual Question Answering on MedXpertQA
Loading...
56
Accuracy
GEMINI-3-FLASH
16.8856
27.0403
37.195
47.3497
Dec 5, 2025
Dec 14, 2025
Dec 23, 2025
Jan 2, 2026
Jan 11, 2026
Jan 20, 2026
Jan 30, 2026
Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
GEMINI-3-FLASH
Model Type=Proprietary
2026.01
56
GPT-5
Model Type=Proprietary
2026.01
54.8
QWEN3-VL-8B-INSTRUCT + MED-SCOUT
Parameters=8B, Enhance...
2026.01
30.8
QWEN3-VL-8B-INSTRUCT
Parameters=8B
2026.01
30.4
LINGSHU-7B + MED-SCOUT
Parameters=7B, Enhance...
2026.01
28
QWEN3-VL-4B-INSTRUCT + MED-SCOUT
Parameters=4B, Enhance...
2026.01
27.7
LINGSHU-7B
Parameters=7B
2026.01
27.4
QWEN3-VL-4B-INSTRUCT
Parameters=4B
2026.01
27
MedTutor-R1
Backbone=Qwen2.5VL-7B-...
2025.12
25.1
QWEN2.5-VL-3B-INSTRUCT
Parameters=3B
2026.01
24.3
HUATUOGPT-VISION-7B + MED-SCOUT
Parameters=7B, Enhance...
2026.01
22.7
MedTutor-R1 w/ LLaVA-based
Backbone=LLaVA
2025.12
22.67
INTERNVL3-8B
Parameters=8B
2026.01
22.4
HUATUOGPT-VISION-7B
Parameters=7B
2026.01
22.4
MEDGEMMA-4B-IT
Parameters=4B
2026.01
22
QWEN2.5-VL-7B-INSTRUCT
Parameters=7B
2026.01
21.9
MedTutor-R1 w/o RL
Reinforcement Learning...
2025.12
20.8
LLAVA-MED-7B
Parameters=7B
2026.01
19.9
Qwen2.5VL
Backbone=Qwen2.5VL-7B-...
2025.12
18.39
Feedback
Search any
task
Search any
task